船舶装备物联网移动信息长距离传输能耗预测方法

Prediction method for long distance transmission energy consumption of ship equipment and Internet of things based on mobile information technology

通常使用最小二乘法预测船舶装备物联网移动信息在输送时产生的能耗,在预测长距离运输和长时间运输能耗时,该方法的预测能力很低,准确性很差,容易产生误差。为了解决此问题,提出了嵌入式预测法,由应用层、数据层和预测层组成预测系统,预测流程分为预测模板设置、预测条件确认、预测方式选择和预测数据异常分析4步。通过对比实验结果可知,在相同时间和相同距离下,嵌入式预测法的预测能力要优于最小二乘法,准确性更高,与实际值更加吻合。

The least square method is used to predict the energy consumption generated by the mobile information of the ship's equipment network, and the prediction ability of the method is very low, the accuracy is poor, and the error is easy to be caused by the prediction of long distance transportation and long time transportation. In order to solve this problem, an embedded prediction method is proposed, which consists of application layer, data layer and prediction layer. The prediction process is divided into four steps: prediction template setting, prediction condition confirmation, prediction mode selection and prediction data anomaly analysis. The experimental results show that the prediction ability of the embedded prediction method is better than the least square method at the same time and the same distance, which is more accurate and more consistent with the actual value.